Exposure to low-dose ambient fine particulate matter PM2.5 and Alzheimer’s disease, non-Alzheimer’s dementia, and Parkinson’s disease in North Carolina

Alzheimer’s disease (AD), non-AD dementia, and Parkinson’s disease (PD) are increasingly common in older adults, yet all risk factors for their onset are not fully understood. Consequently, environmental exposures, including air pollution, have been hypothesized to contribute to the etiology of neurodegeneration. Because persistently elevated rates of AD mortality in the southern Piedmont area of North Carolina (NC) have been documented, we studied mortality and hospital admissions for AD, non-AD dementia, and PD in residential populations aged 65+ with long-term exposures to elevated levels of ambient air particulate matter 2.5 (PM2.5) exceeding the World Health Organization (WHO) air quality standards (≥10μg/m3). Health data were obtained from the State Center for Health Statistics and the Healthcare Cost and Utilization Project. PM2.5 levels were obtained from the MODIS/MISR and SeaWiFS datafiles. Residents in the Study group of elevated air particulate matter (87 zip codes with PM2.5≥10μg/m3) were compared to the residents in the Control group with low levels of air particulate matter (81 zip codes with PM2.5≤7.61μg/m3), and were found to have higher age-adjusted rates of mortality and hospital admissions for AD, non-AD dementia, and PD, including a most pronounced increase in AD mortality (323/100,000 vs. 257/100,000, respectively). After adjustment for multiple co-factors, the risk of death (odds ratio, or OR) from AD in the Study group (OR = 1.35, 95%CI[1.24–1.48]) was significantly higher than ORs of non-AD dementia or PD (OR = 0.97, 95%CI[0.90–1.04] and OR = 1.13, 95%CI[0.92–1.31]). The OR of hospital admissions was significantly increased only for AD as a primary case of hospitalization (OR = 1.54, 95%CI[1.31–1.82]). Conclusion: NC residents aged 65+ with long-term exposures to ambient PM2.5 levels exceeding the WHO standard had significantly increased risks of death and hospital admissions for AD. The effects for non-AD dementia and PD were less pronounced.

Prediction of air particulate matter in Beijing, China, based on the improved particle swarm optimization algorithm and long short-term memory neural network

Intelligent algorithms using deep learning can help learn feature data with nonlinearity and uncertainty, such as time-series particle concentration data. This paper proposes an improved particle swarm optimization (IPSO) algorithm using nonlinear decreasing weights to optimize the hyperparameters, such as the number of hidden layer neurons, learning rate, and maximum number of iterations of the long short-term memory (LSTM) neural network, to predict the time series for air particulate concentration and capture its data dependence. The IPSO algorithm uses nonlinear decreasing weights to make the inertia weights nonlinearly decreasing during the iteration process to improve the convergence speed and capability of finding the global optimization of the PSO. This study addresses the limitations of the traditional method and exhibits accurate predictions. The results of the improved algorithm reveal that the root means square, mean absolute percentage error, and mean absolute error of the IPSO-LSTM model predicted changes in six particle concentrations, which decreased by 1.59% to 5.35%, 0.25% to 3.82%, 7.82% to 13.65%, 0.7% to 3.62%, 0.01% to 3.55%, and 1.06% to 17.21%, respectively, compared with the LSTM and PSO-LSTM models. The IPSO-LSTM prediction model has higher accuracy than the other models, and its accurate prediction model is suitable for regional air quality management and effective control of the adverse effects of air pollution.